学习经验分享之五：YOLOv5数据集划分以及YOLO格式转换

 问    题：有不少学YOLOv5算法的朋友咨询我，发现部分朋友犯了一个很大的错误，就是只是划分了训练集和验证集，没有测试集，并且没有意识到自己的实验设置是错误的、不科学的，这是非常可怕的，意味着可能前期的工作都白做了，浪费了宝贵的时间和精力，部分没有服务器的朋友，还浪费了大量的金钱。所以有必要更新一下YOLOv5算法数据集的随机划分。一般训练集：验证集：测试集=6:2:2（参考一本人工智能的书籍划分的比例，也根据个人数据集的大小灵活把握）。

方   法：

  首先对数据集的文件进行划分，trainval_percent = 0.8，train_percent = 3/4，这个参数设置就是按照6:2:2的比例进行了划分。然后再根据前面写的博客进行索引。学习经验分享之三：YOLOv5训练数据集路径索引_人工智能算法研究院的博客-CSDN博客

import os
import random
import argparse

parser = argparse.ArgumentParser()
parser.add_argument('--xml_path', default=r'D:\AI\NWPU-10\yolo-format', type=str, help='input txt label path')
parser.add_argument('--txt_path', default=r'D:\AI\NWPU-10\ImageSets\Main', type=str, help='output txt label path')
opt = parser.parse_args()

trainval_percent = 0.8
train_percent = 3/4
xmlfilepath = opt.xml_path
txtsavepath = opt.txt_path
total_xml = os.listdir(xmlfilepath)
if not os.path.exists(txtsavepath):
    os.makedirs(txtsavepath)

num = len(total_xml)
list_index = range(num)
tv = int(num * trainval_percent)
tr = int(tv * train_percent)
trainval = random.sample(list_index, tv)
train = random.sample(trainval, tr)

file_trainval = open(txtsavepath + '/trainval.txt', 'w')
file_test = open(txtsavepath + '/test.txt', 'w')
file_train = open(txtsavepath + '/train.txt', 'w')
file_val = open(txtsavepath + '/val.txt', 'w')

for i in list_index:
    name = total_xml[i][:-4] + '\n'
    if i in trainval:
        file_trainval.write(name)
        if i in train:
            file_train.write(name)
        else:
            file_val.write(name)
    else:
        file_test.write(name)

file_trainval.close()
file_train.close()
file_val.close()
file_test.close()

很多朋友都是自己标注的，格式基本为XML格式，故附上yolo格式的转换代码。需要的自取。

# -*- codeing = utf-8 -*-
# @Time : 2021/9/30 10:21
# @Auther : zqk
# @File : voc_labelhrsc.py
# @Software: PyCharm

import xml.etree.ElementTree as ET
import os
from os import getcwd

sets = ['train', 'val', 'test']
classes = ["airplane","airport","baseballfield","basketballcourt","bridge","chimney","dam","expresswayservicearea",
"expresswaytollstation","golfcourse","groundtrackfield","harbor","overpass","ship","stadium","storagetank",
        "tenniscourt","trainstation","vehicle","windmill"]   # 改成自己的类别
abs_path = os.getcwd()
print(abs_path)

def convert(size, box):
    dw = 1. / (size[0])
    dh = 1. / (size[1])
    x = (box[0] + box[1]) / 2.0 - 1
    y = (box[2] + box[3]) / 2.0 - 1
    w = box[1] - box[0]
    h = box[3] - box[2]
    x = x * dw
    w = w * dw
    y = y * dh
    h = h * dh
    return x, y, w, h

def convert_annotation(image_id):
    in_file = open('ZQK_data/Annotations/%s.xml' % (image_id), encoding='UTF-8')
    out_file = open('ZQK_data/labels/%s.txt' % (image_id), 'w')
    tree = ET.parse(in_file)
    root = tree.getroot()
    size = root.find('size')
    w = int(size.find('width').text)
    h = int(size.find('height').text)
    for obj in root.iter('object'):
        difficult = obj.find('difficult').text

        cls = obj.find('name').text
        if cls not in classes or int(difficult) == 1:
            continue
        cls_id = classes.index(cls)
        xmlbox = obj.find('bndbox')
        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
             float(xmlbox.find('ymax').text))
        b1, b2, b3, b4 = b
        # 标注越界修正
        if b2 > w:
            b2 = w
        if b4 > h:
            b4 = h
        b = (b1, b2, b3, b4)
        bb = convert((w, h), b)
        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')

wd = getcwd()
for image_set in sets:
    # if not os.path.exists('ZQK_data/labels/'):
    #     os.makedirs('ZQK_data/labels/')
    image_ids = open('RSOD/ImageSets/Main/%s.txt' % (image_set)).read().strip().split()
    list_file = open('RSOD/ImageSets/%s.txt' % (image_set), 'w')
    for image_id in image_ids:
        list_file.write(abs_path + '/RSOD/JPEGImages/%s.jpg\n' % (image_id))
        # convert_annotation(image_id)
    list_file.close()

最后，希望有兴趣的可以关注一下，后续会出更多相关内容，感谢支持。另外有问题可以进行留言或者私信，我将抽时间进行更新博客统一回答！